Skip to content

P
Paddle-Lite

PaddlePaddle / Paddle-Lite

通知 331
Star 4
Fork 1
P
Paddle-Lite
提交 a2fededf 编写于 作者: 开心的小妮's avatar 开心的小妮
浏览文件
操作

add support CopyFromCpu / CopyToCpu. test=develop

上级 a8e13aae
显示空白变更内容
内联 并排
Showing with 3 addition and 0 deletion
lite/api/paddle_api.cc
浏览文件 @ a2fededf
......@@ -126,11 +126,13 @@ template void Tensor::CopyFromCpu<int, TargetType::kHost>(const int *);
template void Tensor::CopyFromCpu<float, TargetType::kHost>(const float *);
template void Tensor::CopyFromCpu<int8_t, TargetType::kHost>(const int8_t *);
template void Tensor::CopyFromCpu<uint8_t, TargetType::kHost>(const uint8_t *);
template void Tensor::CopyFromCpu<int64_t, TargetType::kHost>(const int64_t *);
template void Tensor::CopyFromCpu<int, TargetType::kARM>(const int *);
template void Tensor::CopyFromCpu<float, TargetType::kARM>(const float *);
template void Tensor::CopyFromCpu<int8_t, TargetType::kARM>(const int8_t *);
template void Tensor::CopyFromCpu<uint8_t, TargetType::kARM>(const uint8_t *);
template void Tensor::CopyFromCpu<int64_t, TargetType::kARM>(const int64_t *);
template void Tensor::CopyFromCpu<int, TargetType::kCUDA>(const int *);
template void Tensor::CopyFromCpu<int64_t, TargetType::kCUDA>(const int64_t *);
......@@ -141,6 +143,7 @@ template void Tensor::CopyToCpu(float *) const;
template void Tensor::CopyToCpu(int *) const;
template void Tensor::CopyToCpu(int8_t *) const;
template void Tensor::CopyToCpu(uint8_t *) const;
template void Tensor::CopyToCpu(int64_t *) const;
shape_t Tensor::shape() const {
return ctensor(raw_tensor_)->dims().Vectorize();
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或